INDEX

Explanations

punctuation marks that indicate the end of thoughts or sentences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ranean

-0.57

lavia

-0.56

ыре

-0.55

 they

-0.55

 California

-0.54

 Engle

-0.54

 They

-0.54

He

-0.53

 people

-0.52

POSITIVE LOGITS

 furthermore

0.91

 således

0.91

withstanding

0.90

 Accordingly

0.89

 ciertamente

0.89

Примеча

0.87

 indeed

0.87

 moreover

0.86

 accordingly

0.86

 Needless

0.85

Activations Density 0.603%

punctuation marks that indicate the end of thoughts or sentences

No Comments

No Known Activations